Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5040
    Prev
    Next
    INDEX
    Explanations

    words related to balance or equilibrium

    oai_token-act-pair · gpt-3.5-turbo

    terms related to load balancing and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENTION
    -0.73
    ICLE
    -0.72
    naire
    -0.70
    Page
    -0.70
     Legacy
    -0.69
    ALK
    -0.69
    Construct
    -0.68
    REE
    -0.68
     plural
    -0.68
     Halls
    -0.68
    POSITIVE LOGITS
    anches
    0.94
    ancers
    0.86
     bal
    0.86
    anca
    0.82
    onies
    0.80
    unker
    0.79
    ancer
    0.79
    atable
    0.78
    ayers
    0.78
    zers
    0.78
    Activations Density 0.004%

    No Known Activations